© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207157
    Prev
    Next
    INDEX
    Explanations

    can you tell

    np_acts-logits-general · gemini-2.5-flash-lite

    provides hydration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Prototype
    0.45
     fürs
    0.43
     bun
    0.41
     lũ
    0.41
    劈
    0.41
    ิก
    0.40
     Paulista
    0.39
     পার্টি
    0.39
    毫不
    0.39
    Situated
    0.39
    POSITIVE LOGITS
    :
    0.45
    orie
    0.45
    ::
    0.44
     intelig
    0.44
    ories
    0.44
    edu
    0.44
    のマ
    0.44
    peda
    0.44
    pend
    0.44
    娍
    0.43
    Activations Density 0.000%

    No Known Activations